get_cohort_distribution

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The readOnlyHint annotation already covers the safety profile, so the description does not need to restate that. 'Computed from raw observations' adds useful provenance context beyond the annotation, but the description does not clarify outlier definition, cohort fixedness, or behavior for empty/missing data. Acceptable but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact sentences with no redundancy. The primary purpose and output statistics are front-loaded, and the second sentence adds a single high-value behavioral note about raw observations.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with one optional parameter, a read-only annotation, and an output schema, the description provides enough information to invoke it correctly. It could add context about the exact cohort definition or outlier computation, but those are not required for a successful call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the schema already documents the metric parameter, its default ('leverage'), and allowed values. The description only refers to 'a given metric' and adds no parameter-level semantics beyond what the schema provides, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States exactly what it computes ('Get cohort metric distribution') and lists the precise statistics returned (min, p10, p25, median, p75, p90, max, mean, std, outliers) plus the scope ('50-operator cohort'). This clearly distinguishes it from per-operator tools like get_operator_profile or aggregate summary tools, even though no sibling is named.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'across the 50-operator cohort' phrasing gives clear context for when to use this tool: when a distribution-level view of a metric across the cohort is needed. It does not explicitly mention when not to use it or name alternative tools, so it stops short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.